370953729b
- perf_stats aggregator lives in eval/, not model/: the import failed silently and EVERY perf column was empty (not just ttft). Now warns on stderr instead of swallowing. - repeats > 1 get their own checkpoint key (:rep2, :rep3, ...): repeat 2 previously restored repeat 1's predictions and finished instantly with identical scores. rep1 keeps the legacy key (existing checkpoints still resume). - repeats summary: report the MEAN score and aggregate time/tokens over ALL runs (was: last run only). - README: six-benchmark command as the primary example. Co-Authored-By: Claude <noreply@anthropic.com>
28 lines
816 B
Python
28 lines
816 B
Python
"""Winogrande (official source: allenai/winogrande, winogrande_xl)."""
|
|
|
|
from ..sample import Sample
|
|
from ..registry import register_dataset
|
|
from ..spec import DatasetSpec
|
|
|
|
|
|
@register_dataset(
|
|
DatasetSpec(
|
|
name='winogrande',
|
|
source='allenai/winogrande', # official: https://huggingface.co/datasets/allenai/winogrande
|
|
subset='winogrande_xl',
|
|
split='validation',
|
|
task_type='mcq',
|
|
tags=['commonsense', 'coreference'],
|
|
description='Winogrande XL binary coreference (official).',
|
|
)
|
|
)
|
|
def winogrande():
|
|
def to_sample(record: dict) -> Sample:
|
|
return Sample(
|
|
input=record['sentence'],
|
|
choices=[record['option1'], record['option2']],
|
|
target={'1': 'A', '2': 'B'}[record['answer']],
|
|
)
|
|
|
|
return to_sample
|